1
Msc. student, Electrical and Computer Engineering, Semnan University
2
Electrical and Computer Engineering Department, Semnan University
Abstract
There are challenges such as depth perception and self-occlusion, in the field of 3D human pose estimation and reconstruction which obstructs precise estimation of body joints. In this paper, we first extract human pose by focusing on 2D ground-truth using sparse coding and. In the second approach, we use a learning-based Convolutional Neural Networks using sparse coding and a model based rectifier to extract the estimated pose. Pose estimation by proposedmethod has reduced the mean error of the reconstruction in comparison with the state of the artworks.
Alikarami, H., Yaghmaee, F., & fadaiee eslam, M. J. (2020). 3D Human Pose Estimation on a 2D Image using Convolutional Neural Networks and Sparse Coding. Journal of Machine Vision and Image Processing, 6(2), 27-41.
MLA
Hassan Alikarami; Farzin Yaghmaee; mohammad javad fadaiee eslam. "3D Human Pose Estimation on a 2D Image using Convolutional Neural Networks and Sparse Coding". Journal of Machine Vision and Image Processing, 6, 2, 2020, 27-41.
HARVARD
Alikarami, H., Yaghmaee, F., fadaiee eslam, M. J. (2020). '3D Human Pose Estimation on a 2D Image using Convolutional Neural Networks and Sparse Coding', Journal of Machine Vision and Image Processing, 6(2), pp. 27-41.
VANCOUVER
Alikarami, H., Yaghmaee, F., fadaiee eslam, M. J. 3D Human Pose Estimation on a 2D Image using Convolutional Neural Networks and Sparse Coding. Journal of Machine Vision and Image Processing, 2020; 6(2): 27-41.